metadata
license: apache-2.0
base_model: neuralhaven/KDRSSC_ViT2TinyViT
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: KDRSSC_ViT2TinyViT-RESISC45_FT
results: []
KDRSSC_ViT2TinyViT-RESISC45_FT
This model is a fine-tuned version of neuralhaven/KDRSSC_ViT2TinyViT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2192
- Accuracy: 0.9403
- Precision: 0.9412
- Recall: 0.9410
- F1: 0.9406
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 512
- eval_batch_size: 512
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 3.1125 | 1.0 | 37 | 0.9645 | 0.911 | 0.9167 | 0.9076 | 0.9069 |
| 0.6036 | 2.0 | 74 | 0.2854 | 0.938 | 0.9387 | 0.9394 | 0.9370 |
| 0.4344 | 3.0 | 111 | 0.2315 | 0.942 | 0.9412 | 0.9422 | 0.9395 |
| 0.3572 | 4.0 | 148 | 0.1993 | 0.948 | 0.9480 | 0.9487 | 0.9464 |
| 0.3086 | 5.0 | 185 | 0.2025 | 0.94 | 0.9405 | 0.9391 | 0.9372 |
| 0.2906 | 6.0 | 222 | 0.1979 | 0.939 | 0.9394 | 0.9381 | 0.9358 |
| 0.2567 | 7.0 | 259 | 0.1814 | 0.943 | 0.9427 | 0.9440 | 0.9413 |
| 0.2785 | 8.0 | 296 | 0.1563 | 0.948 | 0.9470 | 0.9484 | 0.9464 |
| 0.2462 | 9.0 | 333 | 0.1509 | 0.951 | 0.9508 | 0.9524 | 0.9501 |
| 0.245 | 10.0 | 370 | 0.1489 | 0.949 | 0.9475 | 0.9492 | 0.9468 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1